| Finding clusters and components by unsupervised learning | p. 1 |
| Kernel methods for exploratory pattern analysis : a demonstration on text data | p. 16 |
| The use of graph techniques for identifying objects and scenes in indoor building environments for mobile robots | p. 30 |
| Graphical-based learning environments for pattern recognition | p. 42 |
| Spectral analysis of complex Laplacian matrices | p. 57 |
| Decision tree structures for graph database filtering | p. 66 |
| A significant improvement of softassign with diffusion kernels | p. 76 |
| Structural perceptrons for attributed graphs | p. 85 |
| Eigenspace method by autoassociative networks for object recognition | p. 95 |
| A novel constraint-based approach to online graphics recognition | p. 104 |
| Extraction of skeletal shape features using a visual attention operator | p. 114 |
| Computing the cyclic edit distance for pattern classification by ranking edit paths | p. 125 |
| Contour segments from spline interpolation | p. 134 |
| Steady state random walks for path estimation | p. 143 |
| Learning of form models from exemplars | p. 153 |
| An optimal probabilistic graphical model for point set matching | p. 162 |
| A new variational framework for rigid-body alignment | p. 171 |
| An error-tolerant approximate matching algorithm for attributed planar graphs and its application to fingerprint classification | p. 180 |
| Comparison of algorithms for Web document clustering using graph representations of data | p. 190 |
| Heat kernels, manifolds and graph embedding | p. 198 |
| A syntactic pattern recognition approach to computer assisted translation | p. 207 |
| GIATI : a general methodology for finite-state translation using alignments | p. 216 |
| A coupled relaxation method for finding perceptual structures | p. 224 |
| A comparison of unsupervised shot classification algorithms for news video segmentation | p. 233 |
| Diagnosis of lung nodule using the semivariogram function | p. 242 |
| Dictionary-based syntactic pattern recognition using tries | p. 251 |
| Improving probabilistic automata learning with additional knowledge | p. 260 |
| Distances between distributions : comparing language models | p. 269 |
| A new uniform translocation distance | p. 278 |
| Understanding human-computer interactions in map revision | p. 287 |
| Multiscale curvature assessment of postural deviations | p. 296 |
| Modelling human shape with articulated shape mixtures | p. 304 |
| Learning people movement model from multiple cameras for behaviour recognition | p. 315 |
| A comparison of least squares and spectral methods for attributed graph matching | p. 325 |
| An auction algorithm for graph-based contextual correspondence matching | p. 334 |
| Segmentation graph hierarchies | p. 343 |
| Clustering variable length sequences by Eigenvector decomposition using HMM | p. 352 |
| A kernel view of spectral point pattern matching | p. 361 |
| Neural networks for improved target differentiation with sonar | p. 370 |
| An MCMC feature selection technique for characterizing and classifying spatial region data | p. 379 |
| Human action recognition by inference of stochastic regular grammars | p. 388 |
| Optimizing classification ensembles via a genetic algorithm for a Web-based educational system | p. 397 |
| A structural approach to adaptive inverse halftoning for document images | p. 407 |
| Syntactic modeling and recognition of document images | p. 416 |
| Symbols recognition system for graphic documents combining global structural approaches and using a XML representation of data | p. 425 |
| Sketch recognition based on topological spatial relationship | p. 434 |
| A study on the consistency of features for on-line signature verification | p. 444 |
| Statistical structure of natural 4 x 4 image patches | p. 452 |
| Grey scale skeletonisation with curvature sensitive noise damping | p. 461 |
| License vehicle plates localization using maximum correlation | p. 470 |
| Adaptive context for a discrete universal denoiser | p. 477 |
| Pose estimation from airborne video sequences using a structural approach for the construction of homographies and fundamental matrices | p. 486 |
| Temporal post-processing of decision tree outputs for sports video categorisation | p. 495 |
| A new method of polyline approximation | p. 504 |
| On extending symmetry sets for 2D shapes | p. 512 |
| Structural analysis and matching of shape by logical property | p. 521 |
| Scale descriptors through phase unwrapping | p. 530 |
| Lung segmentation on postero-anterior digital chest radiographs using active contours | p. 538 |
| Emotion recognition from dance image sequences using contour approximation | p. 547 |
| Matching concavity trees | p. 556 |
| Combining classifier for face identification at unknown views with a single model image | p. 565 |
| A Logodds criterion for selection of diagnostic tests | p. 574 |
| Evaluation of classical and novel ensemble methods for handwritten word recognition | p. 583 |
| Improving support vector classification via the combination of multiple sources of information | p. 592 |
| Fusing segmentation and classification from multiple features | p. 601 |
| A classifier combination tree algorithm | p. 609 |
| Bounds for the average generalization error of the mixture of experts neural network | p. 618 |
| An effective EM algorithm for PCA mixture model | p. 626 |
| EM initialisation for Bernoulli mixture learning | p. 635 |
| A new family of weak estimators for training in non-stationary distributions | p. 644 |
| Path relinking particle filter for human body pose estimation | p. 653 |
| Clustering with soft and group constraints | p. 662 |
| Learning from general label constraints | p. 671 |
| Solving the one-class problem using neighbourhood measures | p. 680 |
| Detection of a single texture in colour images | p. 689 |
| Clustering based under-sampling for improving speaker verification decisions using AdaBoost | p. 698 |
| Control of sparseness for feature selection | p. 707 |
| On prediction mechanisms in fast branch & bound algorithms | p. 716 |
| Structures of covariance matrix in handwritten character recognition | p. 725 |
| Statistical machine translation decoding using target word reordering | p. 734 |
| Classifier design for population and sensor drift | p. 744 |
| A cost-sensitive paradigm for multiclass to binary decomposition schemes | p. 753 |
| Cost-based classifier evaluation for imbalanced problems | p. 762 |
| A two-stage classifier with reject option for text categorisation | p. 771 |
| Misclassification probability estimations for linear decision functions | p. 780 |
| Generalized variable-kernel similarity metric learning | p. 788 |
| Approximate gradient direction metric for face authentication | p. 797 |
| The imbalanced training sample problem : under or over sampling? | p. 806 |
| Automatic preference mining through learning user profile with extracted information | p. 815 |
| A computational study of naive Bayesian learning in anti-spam management | p. 824 |
| Kernel-based non-linear template matching | p. 831 |
| Analyzing weight distribution of feedforward neural networks and efficient weight initialization | p. 840 |
| One-class support vector machines with a conformal kernel : a case study in handling class imbalance | p. 850 |
| Automatic labeling of sports video using umpire gesture recognition | p. 859 |
| Comparison of two fast nearest-neighbour search methods in high-dimensional large-sized databases | p. 868 |
| A shallow description framework for musical style recognition | p. 876 |
| A nearest neighbor method using bisectors | p. 885 |
| Distance based strategy for supervised document image classification | p. 894 |
| Identification of humans using robust biometric features | p. 903 |
| Facial expression recognition based on the two-dimensional structures of affect | p. 912 |
| Clustering using WCC models | p. 921 |
| Algorithms for constructing min-max partitions of the parameter space for MDL inference | p. 930 |
| Preclustering of electrocardiographic signals using left-to-right hidden Markov models | p. 939 |
| Graph-based clustering of random point set | p. 948 |
| Cluster validity and stability of clustering algorithms | p. 957 |
| Bagging classification models with reduced bootstrap | p. 966 |
| Multiple classifier prediction improvements against imbalanced datasets through added synthetic examples | p. 974 |
| Automatic design of cascaded classifiers | p. 983 |
| Recognition of handwritten numerals using a combined classifier with hybrid features | p. 992 |
| Generating classifier outputs with fixed diversity for evaluating voting methods | p. 1001 |
| Feature selection using improved mutual information for text classification | p. 1010 |
| Feature subset selection using an optimized hill climbing algorithm for handwritten character recognition | p. 1018 |
| Feature shaving for spectroscopic data | p. 1026 |
| Feature selection by Markov chain Monte Carlo sampling - a Bayesian approach | p. 1034 |
| Classifier-independent visualization of supervised data structures using a graph | p. 1043 |
| Texel-based texture synthesis with bunch sampling | p. 1052 |
| Towards 3-dimensional pattern recognition | p. 1061 |
| A general strategy for hidden Markov chain parameterisation in composite feature-spaces | p. 1069 |
| Tracking the evolution of a tennis match using hidden Markov models | p. 1078 |
| Local features for speaker recognition | p. 1087 |
| Selection/extraction of spectral regions for autofluorescence spectra measured in the oral cavity | p. 1096 |
| Kernel relative principal component analysis for pattern recognition | p. 1105 |
| Dynamic character model generation for document keyword spotting | p. 1114 |
| Texture classification by combining wavelet and contourlet features | p. 1126 |
| Distance measures between attributed graphs and second-order random graphs | p. 1135 |
| On not making dissimilarities Euclidean | p. 1145 |
| Content structure discovery in educational videos using shared structures in the hierarchical hidden Markov models | p. 1155 |
| Table of Contents provided by Blackwell. All Rights Reserved. |
